COVID-19 Analysis
Katie Forthman
Wed May 13 09:58:18 2020
Click here for interactive plots:
Click here to see how cities and counties overlap:
Compare COVID stats to Neighborhood Factors
data.cor <- cor(county.Demo_and_Covid.allcounties[,-1], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
Compare COVID stats to 500 cities data and Neighborhood Factors
data.cor2 <- cor(county.Demo_and_Covid.500counties[,-c(1:2)], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor2, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
corrplot.mixed(data.cor2[7:13,c(1:5, 14:42,6)], upper = 'ellipse', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
—-Linear Mixed Effects Model —-
this.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)", data = county.Demo_and_Covid.500counties)## Warning: Some predictor variables are on very different scales: consider
## rescaling
## Warning: Some predictor variables are on very different scales: consider
## rescalingprint(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -1111.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.8441 -0.3481 -0.0853 0.1822 5.4640
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000001466 0.001211
## Residual 0.000014727 0.003838
## Number of obs: 169, groups: stateID, 32
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0100527564 0.0101784349 69.0935729020
## Affluence 0.0048776447 0.0011670489 97.8141213034
## Singletons.in.Tract 0.0016429079 0.0009999260 132.8252073221
## Seniors.in.Tract 0.0010308939 0.0013022302 143.6050000387
## African.Americans.in.Tract 0.0004283729 0.0010920384 146.5280559891
## Noncitizens.in.Tract 0.0008959363 0.0008154113 117.8935838008
## High.BP 0.0002322437 0.0002032372 95.2298252738
## Binge.Drinking 0.0001601397 0.0001668391 39.5136811053
## Cancer -0.0010586382 0.0011701638 95.0090630514
## Asthma 0.0006060166 0.0005845274 38.0987774567
## Heart.Disease 0.0011815085 0.0013752538 67.4605359577
## COPD -0.0002282969 0.0011569133 68.5590444867
## Smoking -0.0001158573 0.0002423892 72.0962296283
## Diabetes -0.0006224878 0.0005760877 69.9236546922
## No.Physical.Activity -0.0000148891 0.0002172336 80.2444495425
## Obesity 0.0002384461 0.0001860310 90.0482352115
## Poor.Sleeping.Habits -0.0000076292 0.0001784120 121.1382984657
## Poor.Mental.Health 0.0000130418 0.0004426388 27.8455851283
## Testing_Rate 0.0000005325 0.0000002861 31.6770512262
## Hospitalization_Rate -0.0001074121 0.0000949175 25.7496653310
## t value Pr(>|t|)
## (Intercept) -0.988 0.327
## Affluence 4.179 0.0000636 ***
## Singletons.in.Tract 1.643 0.103
## Seniors.in.Tract 0.792 0.430
## African.Americans.in.Tract 0.392 0.695
## Noncitizens.in.Tract 1.099 0.274
## High.BP 1.143 0.256
## Binge.Drinking 0.960 0.343
## Cancer -0.905 0.368
## Asthma 1.037 0.306
## Heart.Disease 0.859 0.393
## COPD -0.197 0.844
## Smoking -0.478 0.634
## Diabetes -1.081 0.284
## No.Physical.Activity -0.069 0.946
## Obesity 1.282 0.203
## Poor.Sleeping.Habits -0.043 0.966
## Poor.Mental.Health 0.029 0.977
## Testing_Rate 1.861 0.072 .
## Hospitalization_Rate -1.132 0.268
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence 0.148
## Sngltns.n.T -0.002 0.035
## Snrs.n.Trct 0.582 0.381 0.162
## Afrcn.Am..T 0.179 0.160 -0.435 0.168
## Nnctzns.n.T -0.002 0.100 0.042 0.063 -0.082
## High.BP 0.014 0.248 0.082 0.130 -0.105 0.391
## Bing.Drnkng -0.262 -0.171 -0.311 -0.158 0.104 0.042 0.133
## Cancer -0.591 -0.218 0.186 -0.342 -0.076 -0.152 -0.394 -0.122
## Asthma -0.365 -0.212 -0.218 -0.193 0.074 0.089 0.158 -0.021 0.046
## Heart.Dises -0.154 0.083 -0.292 -0.153 0.238 -0.101 -0.025 0.061 -0.461
## COPD 0.554 0.035 0.143 0.276 -0.006 0.286 0.199 0.109 -0.266
## Smoking -0.179 0.136 -0.176 -0.114 -0.069 0.010 -0.091 -0.294 0.087
## Diabetes 0.068 -0.312 -0.152 -0.221 -0.269 -0.313 -0.532 0.054 0.229
## N.Physcl.Ac -0.172 -0.072 0.105 -0.032 -0.039 -0.234 -0.105 0.088 0.477
## Obesity 0.003 0.418 0.395 0.289 0.152 0.195 -0.085 -0.225 0.113
## Pr.Slpng.Hb -0.475 -0.415 0.177 -0.390 -0.388 -0.008 -0.190 0.066 0.157
## Pr.Mntl.Hlt -0.313 0.257 -0.059 -0.044 0.107 -0.192 -0.079 0.066 0.305
## Testing_Rat 0.182 -0.051 -0.046 0.044 0.068 -0.076 -0.008 0.032 -0.180
## Hsptlztn_Rt -0.160 -0.214 -0.090 -0.245 -0.064 -0.122 -0.122 -0.149 0.067
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H Pr.M.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.274
## COPD -0.366 -0.568
## Smoking 0.089 0.221 -0.528
## Diabetes -0.117 -0.253 -0.141 0.266
## N.Physcl.Ac 0.011 -0.391 0.010 -0.338 -0.091
## Obesity -0.272 -0.099 0.172 -0.212 -0.390 -0.056
## Pr.Slpng.Hb 0.075 0.245 -0.198 0.022 -0.015 -0.108 -0.165
## Pr.Mntl.Hlt -0.248 0.092 -0.452 0.085 0.037 0.047 0.087 -0.196
## Testing_Rat -0.358 -0.033 0.182 0.126 0.117 -0.301 0.110 -0.133 -0.074
## Hsptlztn_Rt 0.080 0.085 -0.110 0.083 0.062 -0.015 -0.035 0.022 -0.061
## Tstn_R
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises
## COPD
## Smoking
## Diabetes
## N.Physcl.Ac
## Obesity
## Pr.Slpng.Hb
## Pr.Mntl.Hlt
## Testing_Rat
## Hsptlztn_Rt 0.188
## fit warnings:
## Some predictor variables are on very different scales: consider rescalingTesting Rate
testing.data.state <- compiled.stats[[length(daily_filenames)]][, c("Province_State", "Testing_Rate")]
testing.data.state <- testing.data.state[!is.na(testing.data.state$Testing_Rate),]
testing.data.state <- testing.data.state[order(testing.data.state$Testing_Rate),]
col.state <- rep("pink", nrow(testing.data.state))
avg.test.rate <- mean(testing.data.state$Testing_Rate, na.rm = T)
col.state[testing.data.state$Testing_Rate < avg.test.rate] <- "grey"
col.state[testing.data.state$Province_State == "Oklahoma"] <- "lightblue"
par(mar = c(5,6,4,2))
barplot(testing.data.state$Testing_Rate, names.arg = testing.data.state$Province_State, horiz = T, main = "Testing Rate by State", las = 2, cex.axis = 1, cex.names = 0.5, col = col.state, border = F, xlab = "Total number of people tested per 100,000 persons.")
abline(v = avg.test.rate, col = "red")
text(x = avg.test.rate + 10, y = 1, labels = "Average Testing Rate", adj = c(0, 0.5), col = "red")
Pink highlights the last 14 days.
day.first.case <- min(which(US.total$cases.total > 100))
n.days <- nrow(US.total)
twoweek.col <- c(rep("grey", n.days-day.first.case-13), rep("pink", 14))
par(mar = c(5,5,4,2))
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$rise.cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Cases of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$rise.deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Deaths of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)